Research Training Course - Apps due 9/9

 

View this email in your browser

The UR2PhD Program makes it easier for folks to engage undergraduate students in research by offering programming to equip students with foundational skills they need to succeed.    For undergraduate students:  If you’re planning on working with emerging researchers in your lab, you may want to consider inviting them to participate in UR2PhD’s Undergraduate Research Training Course (URTC). The URTC is a synchronous, virtual course that helps students learn while doing. The URTC teaches students how to read research papers, how to conduct literature searches, and ultimately enables them to practice writing technically.  To participate in the URTC, students must:  Be undergraduate students at a North American institution  Work in groups of 2-4 on the same research project with the same mentor  Be willing and able to attend all synchronous course sessions at the same time as their team  Applications for the fall URTC course are due on September 9.

Summer research fellowship for computer science students- Apps due May 3!

The Cambridge AI Safety Hub would like to invite exceptional computer science students at UF to apply to the upcoming iteration of the Mentorship for Alignment Researchers (MARS), an AI safety fellowship that matches exceptional students and early-career researchers with experienced researchers and academics from AI labs, think tanks, and academia. In July we will be flying out promising students and working professionals to the United Kingdom to participate in a "sprint week" where they will begin a research project that they'll subsequently carry out remotely through September.

We'll have more than 20 projects spanning multiple disciplines, but a few projects we think especially interesting to computer science students are:

• Research with Yossi Gandelsman (Reve) on whether LLMs can predict the layer at which their own neurons appear, detect polysemantic neurons, identify causal connections between two neurons in their own architecture, or anticipate their own attention patterns.
• A project with Lindley Lentati (Cambridge Inference) on reproducible white-box jailbreak monitoring, covering automated attack generation, multi-layer probe aggregation, and streaming token-by-token detection.
• An investigation with Rhea Karty and Jacob Davis (ERA; LASR Labs) of whether steering vectors for traits like confidence and honesty are context-independent or persona-dependent, using LoRA adapters for character-trained models and tracking trait geometry across training checkpoints.
• Work with James Lucassen (Redwood Research) on deferral protocols for AI control — implementing defer-to-trusted in BashArena, developing usefulness monitors, and building methodology to evaluate them.
• Work with Shivam Raval and Luiza Corpaci (Harvard; AMD) on detecting unfaithful formal translations, using Lean-verified equational theories as ground truth and mech-interp methods to locate where translation failures occur.

Applications close on May 3rd. Students can find more information on our program's webpage, caish [dot] org [slash] mars.

Go Gators!
Justin Dollman
Co-Director @ Cambridge AI Safety Hub

App Deadline TODAY ~ NSF-Funded AI & Quantum Research Opportunity ($9,000 Summer Program)

 I wanted to share a summer research opportunity you might be a great fit for.

The CRA-WP Distributed Research Experiences for Undergraduates (DREU), funded by the National Science Foundation (NSF), is offering AI and quantum-focused research opportunities this summer at leading research universities across the U.S. 

Students could get: 

- $9,000 stipend
- 10-week research experience with a faculty mentor
- National cohort with AI or quantum-focused programming
- Opportunity to attend IEEE Quantum Week (for quantum participants)
- Great preparation for graduate school
Deadline: April 15, 2026
👉 Learn more and apply: https://cra.jotform.com/260473239928870